|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |
java.lang.Object edu.cmu.minorthird.text.learn.SpanFE edu.cmu.minorthird.text.learn.SampleFE.AnnotatedSpanFE edu.cmu.minorthird.text.learn.SampleFE.ExtractionFE
public static class SampleFE.ExtractionFE
An extraction-oriented feature extractor to apply to one-token spans, for extraction tasks.
Nested Class Summary |
---|
Nested classes/interfaces inherited from class edu.cmu.minorthird.text.learn.SpanFE |
---|
SpanFE.Filter, SpanFE.Function, SpanFE.Result, SpanFE.SetResult<T>, SpanFE.SpanResult, SpanFE.SpanSetResult, SpanFE.StringBagResult, SpanFE.TokenSetResult |
Field Summary | |
---|---|
protected java.lang.String[] |
tokenPropertyFeatures
|
protected boolean |
useCharType
|
protected boolean |
useCompressedCharType
|
protected int |
windowSize
|
Fields inherited from class edu.cmu.minorthird.text.learn.SpanFE |
---|
annotatorLoader, instance, requiredAnnotation, requiredAnnotationFileToLoad, STORE_AS_BINARY, STORE_AS_COUNTS, STORE_COMPACTLY |
Constructor Summary | |
---|---|
SampleFE.ExtractionFE()
|
|
SampleFE.ExtractionFE(int windowSize)
|
Method Summary | |
---|---|
void |
extractFeatures(Span s)
Implement this with a specific set of SpanFE 'pipelines'. |
void |
extractFeatures(TextLabels labels,
Span s)
Implement this with a specific set of SpanFE 'pipelines'. |
int |
getFeatureWindowSize()
|
java.lang.String |
getTokenPropertyFeatures()
|
boolean |
getUseCharType()
|
boolean |
getUseCompressedCharType()
|
void |
setFeatureWindowSize(int n)
Specify the number of tokens on before and after the span to emit features for. |
void |
setTokenPropertyFeatures(java.util.Set<java.lang.String> propertySet)
|
void |
setTokenPropertyFeatures(java.lang.String commaSeparatedTokenPropertyList)
Specify the token properties from the TextLabels environment that will be used as features. |
void |
setUseCharType(boolean flag)
If set to true, produce features like "token.charTypePattern.Aaaa" for the word "Bill" |
void |
setUseCompressedCharType(boolean flag)
If set to true, produce features like "token.charTypePattern.Aa+" for the word "Bill". |
Methods inherited from class edu.cmu.minorthird.text.learn.SpanFE |
---|
emit, emit, emit, emit, extractInstance, extractInstance, from, from, getAnnotationProvider, getRequiredAnnotation, requireMyAnnotation, setAnnotationProvider, setAnnotatorLoader, setFeatureStoragePolicy, setRequiredAnnotation, setRequiredAnnotation, trace |
Methods inherited from class java.lang.Object |
---|
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait |
Field Detail |
---|
protected int windowSize
protected boolean useCharType
protected boolean useCompressedCharType
protected java.lang.String[] tokenPropertyFeatures
Constructor Detail |
---|
public SampleFE.ExtractionFE()
public SampleFE.ExtractionFE(int windowSize)
Method Detail |
---|
public void setFeatureWindowSize(int n)
public int getFeatureWindowSize()
public void setUseCharType(boolean flag)
public boolean getUseCharType()
public void setUseCompressedCharType(boolean flag)
public boolean getUseCompressedCharType()
public void setTokenPropertyFeatures(java.lang.String commaSeparatedTokenPropertyList)
public java.lang.String getTokenPropertyFeatures()
public void setTokenPropertyFeatures(java.util.Set<java.lang.String> propertySet)
public void extractFeatures(Span s)
SpanFE
extractFeatures
in class SpanFE
public void extractFeatures(TextLabels labels, Span s)
SpanFE
extractFeatures
in class SpanFE
|
|||||||||
PREV CLASS NEXT CLASS | FRAMES NO FRAMES | ||||||||
SUMMARY: NESTED | FIELD | CONSTR | METHOD | DETAIL: FIELD | CONSTR | METHOD |